本笔记来源于B站Up主: 有Li 的影像组学系列教学视频
本节(7)主要介绍: 特征筛选之LASSO回归分析(代码实现)
import pandas as pd
import numpy as np
from sklearn.utils import shuffle
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LassoCV
xlsx1_filePath = 'C:/Users/RONG/Desktop/PythonBasic/data_A.xlsx'
xlsx2_filePath = 'C:/Users/RONG/Desktop/PythonBasic/data_B.xlsx'
data_1 = pd.read_excel(xlsx1_filePath)
data_2 = pd.read_excel(xlsx2_filePath)
rows_1,__ = data_1.shape
rows_2,__ = data_2.shape
data_1.insert(0,'label',[0]*rows_1)
data_2.insert(0,'label',[1]*rows_2)
data = pd.concat([data_1,data_2])
data = shuffle(data)
data = data.fillna(0)
X = data[data.columns[1:]]
y = data['label']
colNames = X.columns
X = X.astype(np.float64)
X = StandardScaler().fit_transform(X) #new knowledge
X = pd.DataFrame(X)
X.columns = colNames
LASSO回归
#LASSO method
alphas = np.logspace(-3,1,50)
print(alphas)
model_lassoCV = LassoCV(alphas = alphas, cv = 10, max_iter = 100000).fit(X,y) #cv, cross-validation
print(model_lassoCV.alpha_)
coef = pd.Series(model_lassoCV.coef_,index = X.columns) #new knowledge
# print(coef)
print("Lasso picked " + str(sum(coef != 0)) + " variables and eliminated the other " + str(sum(coef == 0)))
Output:
# 0.020235896477251564
# Lasso picked 8 variables and eliminated the other 99
index = coef[coef != 0].index
X = X[index]
# print(X.head())
print(coef[coef != 0])
Output:
# original_shape_Flatness 0.251719
# original_glcm_Correlation -0.005528
# original_glcm_Idmn -0.143942
# original_gldm_DependenceEntropy 0.054091
# original_gldm_SmallDependenceLowGrayLevelEmphasis 0.090112
# original_glszm_SmallAreaLowGrayLevelEmphasis 0.185858
# original_ngtdm_Coarseness -0.156813
# original_ngtdm_Strength -0.004631
# dtype: float64
print(model_lassoCV.intercept_)
# > 0.49999999999999994
